Transformers
Table Pre-training via Execution
Introduced by Liu et al. in TAPEX: Table Pre-training via Learning a Neural SQL ExecutorTAPEX is a conceptually simple and empirically powerful pre-training approach to empower existing models with table reasoning skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesising executable SQL queries.
Source: TAPEX: Table Pre-training via Learning a Neural SQL Executor
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Question Answering | 1 | 25.00% |
| Language Modelling | 1 | 25.00% |
| Semantic Parsing | 1 | 25.00% |
| Table-based Fact Verification | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
